财政收入影响因素分析及预测-第三周作业

#-*- coding: utf-8 -*-

# 代码6-1

import numpy as np
import pandas as pd

inputfile = 'D:/Desktop/air_data.csv' # 输入的数据文件
data = pd.read_csv(inputfile) # 读取数据

# 描述性统计分析
description = [data.min(), data.max(), data.mean(), data.std()]  # 依次计算最小值、最大值、均值、标准差
description = pd.DataFrame(description, index = ['Min', 'Max', 'Mean', 'STD']).T  # 将结果存入数据框
print('描述性统计结果：\n',np.round(description, 2))  # 保留两位小数



# 代码6-2

# 相关性分析
corr = data.corr(method = 'pearson')  # 计算相关系数矩阵
print('相关系数矩阵为：\n',np.round(corr, 2))  # 保留两位小数



# 代码6-3

# 绘制热力图
import matplotlib.pyplot as plt
import seaborn as sns
plt.subplots(figsize=(25, 25)) # 设置画面大小 
sns.heatmap(corr, annot=True, vmax=1, square=True, cmap="Blues") 
plt.title('3127')
plt.show()
plt.close

 

 

import pandas as pd
import matplotlib.pyplot as plt
from datetime import datetime
datafile = 'D:/Desktop/air_data.csv'
data = pd.read_csv(datafile)
ffp = data['FFP_DATE'].apply(lambda x:datetime.strptime(x,'%Y/%m/%d'))
ffp_year = ffp.map(lambda x : x.year)
fig = plt.figure(figsize=(12,8))
plt.rcParams['font.sans-serif'] = 'SimHei'
plt.rcParams['axes.unicode_minus'] = False
plt.hist(ffp_year,bins='auto',color='tomato')
plt.xlabel('年份')
plt.ylabel('入会人数')
plt.title('3127各年份入会人数')
plt.show()
plt.close()

 

 

male = pd.value_counts(data['GENDER'])['男']
female = pd.value_counts(data['GENDER'])['女']
fig = plt.figure(figsize=(7,4))
plt.pie([male,female],labels=['男','女'],colors=['gold','purple'],autopct='%1.1f%%')
plt.title('3127会员性别比例')
plt.show()

 

 

lv_four = pd.value_counts(data['FFP_TIER'])[4]
lv_five = pd.value_counts(data['FFP_TIER'])[5]
lv_six = pd.value_counts(data['FFP_TIER'])[6]
fig = plt.figure(figsize=(8,5))
plt.bar(x=range(3),height=[lv_four,lv_five,lv_six],width=0.4,alpha=0.8,color='blue')
plt.xticks([index for index in range(3)],['4','5','6'])
plt.xlabel('会员等级')
plt.ylabel('会员人数')
plt.title('3127会员各级别人数')
plt.show()
plt.close()

 

 

age = data['AGE'].dropna()
age = age.astype('int64')
fig = plt.figure(figsize=(5,10))
plt.boxplot(age,
            patch_artist=True,
            labels=['会员年龄'],
            boxprops={'facecolor':'lightblue'})
plt.title('3127会员年龄分布箱型图')
plt.grid(axis='y')
plt.show()
plt.close()